Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhuangguangdahyh-dotcom/content-ops-studio --skill content-creationgit clone --depth 1 https://github.com/zhuangguangdahyh-dotcom/content-ops-studioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-creation)<a href="https://agentmods.dev/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-creation"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-creation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-creation"><img src="https://agentmods.dev/badge/skills/zhuangguangdahyh-dotcom/content-ops-studio/content-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00986 |
| Opus 5 | $0.00020 | $0.00493 |
| Sonnet 5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
content-creation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Create or revise one evidence-grounded Content Package while keeping conversion cover copy, page-one content copy, and visual production separate.
Required preflight
Call content_ops_get_content_context. Require one PAINPOINT_CONFIRMED target, current Project Profile, Pack and active-rule versions, retained Evidence summaries, historical Content, title-count capability, and a resolved operation. Never treat chat memory as project evidence.
Required tool sequence
- Call
content_ops_plan_content_creationin dry-run mode. Default to at least three material angles and 4–8 pages. - Let the host author one core problem, one core viewpoint, page copy, publish title/body, optional truthful CTA, classified claims, dimension scores, and reasoned near-semantic assessments. For Xiaohongshu, also create a versioned Cover Copy Package with distinct
cover_primary_hook,cover_secondary_line, optional supporting copy, and unchangedpage_1_content_copy. - Call
content_ops_submit_content_draft. This writes only project-local artifacts and binds Plan hash, painpoint version, rule snapshot, and idempotency key. - Show the draft summary and obtain explicit write confirmation before
content_ops_finalize_content_copy. - Finalize validates Schemas, claims, deterministic fingerprint, duplication, title, page structure and quality; it writes one existing-Base Content record, moves the painpoint to
PAINPOINT_CONTENT_IN_PROGRESS, read-verifies, checkpoints, and stops at G3CONTENT_COPY. - Show the exact Content/Copy version and copy. Never infer approval. Only the Router may submit a matching
content-copy-reviewthroughcontent_ops_submit_approval. - Use list/get/verify tools for readback. For changes, call
content_ops_plan_content_revision, retain history, resubmit a new copy version, and wait for a new G3.
Authoring and evidence policy
One Content binds one primary painpoint, core problem, and core viewpoint. It must give the Audience emotional, money, time, risk-reduction, decision, or professional-insight value. External facts and project facts need appropriate Evidence Refs. Professional judgments and opinions must be labelled honestly. Never invent data, studies, rankings, customer stories, cases, or results. An unsupported claim blocks G3.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 540 B
- references/angle-selection.md 285 B
- references/claim-policy.md 309 B
- references/contract.md 354 B
- references/cover-conversion-copy-policy.md 955 B
- references/duplication-policy.md 321 B
- references/examples.md 426 B
- references/failure-handling.md 341 B
- references/g3-review.md 274 B
- references/quality-policy.md 281 B
- references/README.md 270 B
- references/structure-selection.md 324 B
- references/tool-policy.md 337 B
- references/workflow.md 347 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 53 lines · 41 tokens per session scan A 81de7443c1af
content-creation is a skill published in the GitHub repository zhuangguangdahyh-dotcom/content-ops-studio (0 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 986 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gpt-image
Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
weibo-poster
A writing guide for Weibo, a Chinese microblogging platform similar to a short-post social network. It covers concise posts, longer posts, hashtags, @ mentions, image layouts, and posting-time suggestions.
xiaohongshu-writer
A writing guide for Xiaohongshu, a Chinese social platform for short lifestyle and advice posts. It helps shape titles, post structure, emoji use, cover text, and hashtags.
excel-helper
A spreadsheet assistant for Excel, a program used to organize, calculate, and analyze tabular data. It covers formulas, pivot tables, charts, data cleaning, and VBA macros, which are small automation programs for Excel.
word-writer
A writing and formatting assistant for Microsoft Word documents, including reports, contracts, résumés, academic papers, and administrative documents.